The Causal Interpretation of the AKM Estimand

EI Seminar
Campus Woudestein, showcasing the flags of the School's and Institutes.

The Abowd–Kramarz–Margolis (AKM) regression is widely used to analyz=se firm wage premia. We derive a general potential outcome decomposition of the AKM estimand and show that it is a worker-weighted average of causal effects of moving between pairs of firms. 

 

 

Speaker
Daniel Wilhelm
Date
Thursday 7 May 2026, 12:00 - 13:00
Type
Seminar
Room
ET-14
Location
Campus Woudestein
Add to calendar

(with X. Huang, T. Lamadon, M. Mogstad, A. Shaikh)

Under strong assumptions, this decomposition collapses so that the AKM estimand for a specific firm equals the causal effect of moving from the left-out firm to that firm. 

We give necessary and sufficient conditions for the AKM estimand to have this causal interpretation and propose tests for the sufficient conditions. 

n an application to Italian administrative data we document that the standard AKM estimator can be severely biased when these conditions fail. We propose a matched-AKM estimator that consistently estimates causal firm effects under weaker and more realistic assumptions.

See also

Statistical Methods for High-dimensional Dolatility

Mark Podolskij (University of Luxembourg)
Campus Woudestein, showcasing the flags of the School's and Institutes.

Testing for endogeneity of irregular sampling schemes

Giulia Livieri (LSE)
Image - Graph Statistics Stock

Causal Inference and Policy Evaluation

Keynote Speaker: Alberto Abadie
Image of campus Woudestein

Adapting smart waste collection systems through operational learning

Dilay Aktas Dejaegere (KU Leuven)

Uneven buffering of U.S. maize yields against extreme heat - a time-varying coefficient panel approach

Marina Friedrich (Vrije Universiteit Amsterdam)
View of a cornfield

Handling and Exploiting Symmetry in Benders Decomposition

Christopher Hojny (Eindhoven University of Technology)
Campus from above with Mandeville Building

FinEML Conference 2026

Financial Econometrics Meets Machine Learning
Image - University of Geneva
More information

Do you want to know more about the event? Contact the secretariat Econometrics at eb-secr@ese.eur.nl.

Compare @count study programme

  • @title

    • Duration: @duration
Compare study programmes